Cyberatttack Detection and Classification in IIoT systems using XGBoost and Gaussian Naïve Bayes: A Comparative Study

Abstract

The Industrial Internet of Things (IIoT) is experiencing rapid expansion, forming a vast network of interconnected devices, sensors, and machines that generate large volumes of data. In the context of Industry 5.0, ensuring the accuracy and reliability of this data is essential. This paper addresses the challenges of detecting and classifying cyberattacks within the IIoT by employing advanced analytical techniques. Specifically, we explore the application of Machine Learning (ML) algorithms, focusing on the comparison between the XGBoost and Naïve Bayes models. Our study uses the KDD-99 and NSL KDD datasets to evaluate the performance of these models in terms of accuracy, precision, recall, and F1 score. The results demonstrate that the XGBoost model significantly outperforms the Naïve Bayes model across all metrics, achieving an accuracy of 99%. This study contributes to the improvement of intrusion detection and classification of cyberattacks in IIoT environments.